Automated diagnosis of flatfoot using cascaded convolutional neural network for angle measurements in weight-bearing lateral radiographs.

OBJECTIVES: Diagnosis of flatfoot using a radiograph is subject to intra- and inter-observer variabilities. Here, we developed a cascade convolutional neural network (CNN)-based deep learning model (DLM) for an automated angle measurement for flatfoot diagnosis using landmark detection. METHODS: We used 1200 weight-bearing lateral foot radiographs from young adult Korean males for the model development. An experienced orthopedic surgeon identified 22 radiographic landmarks and measured three angles for flatfoot diagnosis that served as the ground truth (GT). Another orthopedic surgeon (OS) and a general physician (GP) independently identified the landmarks of the test dataset and measured the angles using the same method. External validation was performed using 100 and 17 radiographs acquired from a tertiary referral center and a public database, respectively. RESULTS: The DLM showed smaller absolute average errors from the GT for the three angle measurements for flatfoot diagnosis compared with both human observers. Under the guidance of the DLM, the average errors of observers OS and GP decreased from 2.35° ± 3.01° to 1.55° ± 2.09° and from 1.99° ± 2.76° to 1.56° ± 2.19°, respectively (both p < 0.001). The total measurement time decreased from 195 to 135 min in observer OS and from 205 to 155 min in observer GP. The absolute average errors of the DLM in the external validation sets were similar or superior to those of human observers in the original test dataset. CONCLUSIONS: Our CNN model had significantly better accuracy and reliability than human observers in diagnosing flatfoot, and notably improved the accuracy and reliability of human observers. KEY POINTS: • Development of deep learning model (DLM) that allows automated angle measurements for landmark detection based on 1200 weight-bearing lateral radiographs for diagnosing flatfoot. • Our DLM showed smaller absolute average errors for flatfoot diagnosis compared with two human observers. • Under the guidance of the model, the average errors of two human observers decreased and total measurement time also decreased from 195 to 135 min and from 205 to 155 min.

The relationship of preoperative estimated glomerular filtration rate and outcomes after cardiovascular surgery in patients with normal serum creatinine: a retrospective cohort study.

BACKGROUND: Although serum creatinine concentration has been traditionally used as an index of renal function in clinical practice, it is considered relatively inaccurate, especially in patients with mild renal dysfunction. This study investigated the usefulness of preoperative estimated glomerular filtration rate (eGFR) in predicting complications after cardiovascular surgery in patients with normal serum creatinine concentrations. METHODS: This study included 2208 adults undergoing elective cardiovascular surgery. Preoperative eGFR was calculated using Chronic Kidney Disease Epidemiology Collaboration equations. The relationships between preoperative eGFR and 90 day postoperative composite major complications were analyzed, including 90 day all-cause mortality, major adverse cardiac and cerebrovascular events, severe acute kidney injury, respiratory and gastrointestinal complications, wound infection, sepsis, and multi-organ failure. RESULTS: Of the 2208 included patients, 185 (8.4%) had preoperative eGFR < 60 mL/min/1.73 m2 and 328 (14.9%) experienced postoperative major complications. Multivariable logistic regression analyses showed that preoperatively decreased eGFR was independently associated with an increased risk of composite 90 day major postoperative complications (adjusted odds ratio: 1.232; 95% confidence interval [CI]: 1.148-1.322; P <  0.001). eGFR was a better discriminator of composite 90 day major postoperative complications than serum creatinine, with estimated c-statistics of 0.724 (95% CI: 0.694-0.754) for eGFR and 0.712 (95% CI: 0.680-0.744) for serum creatinine (P = 0.008). CONCLUSIONS: Decreased eGFR was significantly associated with an increased risk of major complications after cardiovascular surgery in patients with preoperatively normal serum creatinine concentrations.

Automated landmark identification for diagnosis of the deformity using a cascade convolutional neural network (FlatNet) on weight-bearing lateral radiographs of the foot.

Landmark detection in flatfoot radiographs is crucial in analyzing foot deformity. Here, we evaluated the accuracy and efficiency of the automated identification of flatfoot landmarks using a newly developed cascade convolutional neural network (CNN) algorithm, Flatfoot Landmarks AnnoTating Network (FlatNet). A total of 1200 consecutive weight-bearing lateral radiographs of the foot were acquired. The first 1050 radiographs were used as the training and tuning, and the following 150 radiographs were used as the test sets, respectively. An expert orthopedic surgeon (A) manually labeled ground truths for twenty-five anatomical landmarks. Two orthopedic surgeons (A and B, each with eight years of clinical experience) and a general physician (GP) independently identified the landmarks of the test sets using the same method. After two weeks, observers B and GP independently identified the landmarks once again using the developed deep learning CNN model (DLm). The X- and Y-coordinates and the mean absolute distance were evaluated. The average differences (mm) from the ground truth were 0.60 ± 0.57, 1.37 ± 1.28, and 1.05 ± 1.23 for the X-coordinate, and 0.46 ± 0.59, 0.97 ± 0.98, and 0.73 ± 0.90 for the Y-coordinate in DLm, B, and GP, respectively. The average differences (mm) from the ground truth were 0.84 ± 0.73, 1.90 ± 1.34, and 1.42 ± 1.40 for the absolute distance in DLm, B, and GP, respectively. Under the guidance of the DLm, the overall differences (mm) from the ground truth were enhanced to 0.87 ± 1.21, 0.69 ± 0.74, and 1.24 ± 1.31 for the X-coordinate, Y-coordinate, and absolute distance, respectively, for observer B. The differences were also enhanced to 0.74 ± 0.73, 0.57 ± 0.63, and 1.04 ± 0.85 for observer GP. The newly developed FlatNet exhibited better accuracy and reliability than the observers. Furthermore, under the FlatNet guidance, the accuracy and reliability of the human observers generally improved.

Treatment of rocuronium-induced anaphylaxis using sugammadex - A case report.

BACKGROUND: Perioperative anaphylaxis is a life-threatening clinical condition characterized by severe respiratory and cardiovascular manifestations. Neuromuscular blocking agents are the most common cause of anaphylaxis during anesthesia. CASE: We report a case of rocuronium-induced anaphylaxis treated with sugammadex. A 75-year-old female was scheduled to undergo spinal surgery. She had no history of allergies. After the injection of rocuronium, she developed hypotension and tachycardia, and skin rashes and urticaria appeared. The patient received sugammadex to delay the operation, and her vital signs were stabilized. On the 76th postoperative day, we performed intradermal tests for rocuronium, propofol, and cefazolin. Diluted rocuronium alone induced 14 mm of flare and 8 mm of wheal within 5 min, both of which disappeared within 15 min after the intradermal injection. CONCLUSIONS: Sugammadex is a useful rocuronium antagonist that can be used to treat rocuronium-induced anaphylaxis.

The effects of backward, upward, rightward pressure maneuver for intubation using the OptiscopeTM: a retrospective study.

BACKGROUND: The OptiscopeTM and the backward, upward, rightward pressure (BURP) maneuver are widely used in clinical practice because the BURP maneuver facilitates intubation by improving visualization of the larynx. However, the effect of the BURP maneuver is unclear when using the OptiscopeTM. Therefore, we retrospectively investigated the effect of the BURP maneuver on intubation using the OptiscopeTM. METHODS: Sixty-eight patients intubated with the OptiscopeTM were enrolled. We used the BURP maneuver in Group A (n = 33) and the conventional maneuver (which does not use the BURP maneuver) in Group B (n = 35). BURP application status was a binary variable representing whether the BURP maneuver was used during the intubation. A multiple linear regression analysis was performed to assess the effects of the BURP application status on intubation time controlling for body mass index, preoperative dental injury status, obstructive sleep apnea history, thyromental distance, sternomental distance, interincisor distance, history of neck rotation restriction, and Mallampati classification. RESULTS: There was no difference in the intubation time between the two groups. According to the regression model (R2 = 0.308, P = 0.007), the BURP maneuver (Group A) decreased the intubation time by 6.089 seconds (95% confidence interval 1.303-10.875, P = 0.014) compared to Group B.

Comparison of five glomerular filtration rate estimating equations as predictors of acute kidney injury after cardiovascular surgery.

We aimed to compare the ability of preoperative estimated glomerular filtration rate (eGFR), calculated using five different equations, to predict adverse renal outcomes after cardiovascular surgery. Cohorts of 4,125 adult patients undergoing elective cardiovascular surgery were evaluated. Preoperative eGFR was calculated using the Cockcroft-Gault, Modification of Diet in Renal Disease (MDRD) II, re-expressed MDRD II, Chronic Kidney Disease Epidemiology Collaboration, and Mayo quadratic (Mayo) equations. The primary outcome was postoperative acute kidney injury (AKI), defined by Kidney Disease: Improving Global Outcomes Definition and Staging criteria based on changes in serum creatinine concentrations within 7 days. The MDRD II and Cockcroft-Gault equations yielded the highest (88.1 ± 26.7 ml/min/1.73 m2) and lowest (79.6 ± 25.5 ml/min/1.73 m2) mean eGFR values, respectively. Multivariable analysis showed that a preoperative decrease in renal function according to all five equations was independently associated with an increased risk of postoperative AKI. The area under the receiver operating characteristics curve for predicting postoperative AKI was highest for the Mayo equation (0.713). Net improvements in reclassification and integrated discrimination were higher for the Mayo equation than for the other equations. The Mayo equation was the most accurate in predicting postoperative AKI in patients undergoing cardiovascular surgery.